Stop unsafe agent actions and prove outcomes. Pre-execution authorization and post-execution verification for AI agents.
Two paths: Authority (policy, mandates, sidecar) and Runtime (snapshots, assertions, traces).
Predicate Secure: Quick Start, Installation, Frameworks
Predicate Authority (policy, sidecar) and Predicate Vault (control plane, kill-switches, audit).
Runtime / Verification: SDK Overview, Verifications, Agent Runtime
Predicate Claw: How It Works, Operational Runbook
Control plane: Predicate Vault — centralized policy, kill-switches, and WORM audit for compliance teams.
Authorize actions before side effects, then enforce with deterministic snapshots and assertions
Identity controls, policy enforcement, mandates, revocation, and operational governance.
Identity, policy enforcement, mandates, and operational controls
Zero-trust security wrapper for AI agents with pre- and post-execution verification
Production governance patterns: policy controls, revocation, and audit
Runtime assertions, snapshots, debugging, integrations, and verification APIs.
Install the SDK and add pre-action authority controls in minutes
Build deterministic AI agents with policy-aware action execution
Reference for snapshots, actions, and assertions
Add authority checks and deterministic verification to your existing frameworks
Replay agent runs and inspect policy decisions and assertion outcomes
Understand element selection, actions, and verification
Low-level API for rendered DOM snapshots
Endpoint documentation for direct API access
Start with identity, governance controls, and sidecar operations.
Start with deterministic runtime checks, traces, and framework integrations.
Can't find what you're looking for? Our support team is here to help.